Visit Open-E website
Results 1 to 4 of 4

Thread: Storage License Calculator for Open-E JovianDSS

  1. #1
    Join Date
    Jan 2016
    Posts
    17

    Default Storage License Calculator for Open-E JovianDSS

    Recently we launched a new useful tool for the ZFS-based Open-E JovianDSS, available on our website at no cost. Try the storage License Calculator to check the exact license required for your pools and their groups - either data or non-data groups, for your storage setup with Open-E JovianDSS. All you need to select is:

    • the redundancy level

    • the number of disks in a group

    • the number of groups

    • the size of each disk

    The calculator will automatically display the total necessary license capacity. NOTE: Results are shown for single pools only.

    Calculate capacity now: http://www.open-e.com/r/a7j/
    Last edited by Ka-P; 12-15-2016 at 01:20 PM.

  2. #2
    Join Date
    Sep 2016
    Location
    Kyiv, Ukraine
    Posts
    12

    Default

    Fresh questions regarding performance metrics in calculator at https://www.open-e.com/raid-calculator/joviandss/
    - Which assumptions about the load were made to estimate the performance metrics?
    - Or, at which load the measured real pool performance will be much close to calculated?

    I’m suspecting (basing at the metrics grow while increasing number of the disk groups) the metrics are calculated closer to random request distribution. Am I right?

    Is the metrics for single disk group as the performance of single drive underestimated? In the ‘classic’ method, which I know (for Dell Compellent, EMC VNX, and Dell MD storages) the more drives in a disk group, the more performance that group has (in a single or multiple disk groups array). Does Open-E planning to publish revised results?


  3. #3

    Default

    Hi,

    Answering the first question.
    Yes, the performance metrics is calculated on random request distribution.

    About the second question.
    In ZFS the performance is scaling on a vdev and not on a disk group level.
    So, for example the stripe is populated on vdevs, and therefore the best performance can be achieved with the disks used as singles, but there won't be any redundancy of course.
    The next performance tier would be to use mirror groups, so we have a redundancy on 1 disk in a group.
    More complicated raidz's are giving a better redundancy with the cost of a performance.

  4. #4
    Join Date
    Sep 2016
    Location
    Kyiv, Ukraine
    Posts
    12

    Default

    Thank You, T-Ku, thus, the performance index reflects scaling by the number of disk groups (vdevs, https://www.freebsd.org/doc/handbook/zfs-term.html). Still the disk group performance remains unclear. The calculator help states "The disks in a data group work in unison, which means that their effective performance is the same as one disk, no matter how many there are", which is very ugly in comparison with traditional approach. May be, after more statistics will be available, the calculator will be much optimistic, closer to "Complex RAID Performance" chapter at https://www.storagecraft.com/blog/raid-performance/

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •